--- title: "Kimi K3.1 Pro: Specs, Price, Open Weights Date, and Benchmarks" slug: kimi-k3-1-pro-specs-price-open-weights-benchmarks description: "Moonshot released Kimi K3.1 Pro on October 23 at $2 per million input tokens and $10 per million output, a third less than Kimi K3, with the weights due by November 4. Specs, pricing, Moonshot's benchmark claims, and what it means for the hardware." author: "Yotta Labs" date: 2026-10-24 categories: ["Inference"] canonical: https://www.yottalabs.ai/post/kimi-k3-1-pro-specs-price-open-weights-benchmarks --- # Kimi K3.1 Pro: Specs, Price, Open Weights Date, and Benchmarks ![](https://cdn.sanity.io/images/wy75wyma/production/b9dbe4b3d52809678e9f4708044ec79dd8e2b798-1200x627.png) *Moonshot's follow-up to Kimi K3 is out, and it costs less than the model it replaces. Here's what changed, what didn't, and when you can download it.* Moonshot released Kimi K3.1 Pro on October 23, 2026, calling it the first model in the K3.1 series and its most capable open-weight model to date. It is a post-trained version of [Kimi K3](https://www.yottalabs.ai/post/kimi-k3-specs-benchmarks-how-to-access-2026) with the same architecture and a much larger post-training budget, and it ships with a faster variant, Kimi K3.1 Pro Highspeed. Both are live on the Kimi API today. The full weights are promised by November 4. Two things make this release different from a routine version bump. The price went down, not up: K3.1 Pro is a third cheaper than K3 on every rate. And because the architecture is unchanged, the self-hosting math for K3 applies to K3.1 Pro as written. This post covers the specs, the pricing, what Moonshot claims on benchmarks, and the route to using it now. ## The short version - **Released:** October 23, 2026, on Kimi.com, Kimi Work, Kimi Code, and the Kimi API. - **Architecture:** same as Kimi K3. 2.8 trillion total parameters, 104B active per token, 1M-token context, text and image input. - **API price:** $2.00 per million input tokens, $0.20 per million cached input, $10.00 per million output. Kimi K3 was $3.00 / $0.30 / $15.00. - **Highspeed variant:** $4.00 / $0.20 / $20.00, which Moonshot says runs two to three times faster. - **Open weights:** due by November 4, 2026. License not yet announced. - **Benchmarks:** Moonshot's own numbers put it within a point of Claude Opus 5.5 on Terminal-Bench 4.0 and ahead of GPT-6 Astra on most of the agentic rows. ## The numbers that matter Moonshot describes the gains as coming from post-training: larger-scale reinforcement learning across hundreds of domains, with work on the RL framework, long-context inference, and sandbox infrastructure to make that scale possible. The base model is K3. That matters for anyone planning to run it, and we come back to it below. ## Kimi K3.1 Pro pricing Per million tokens, from Moonshot's API pricing page. Cache writes are billed separately on the K3-series models: $2.00 per million for a five-minute cache and $4.00 for a one-hour cache on K3.1 Pro, double that on Highspeed. Cached reads are billed only at the cache-hit rate. The direction is the point. Moonshot cut the price of its flagship by a third while claiming a large capability jump, and the per-token cost of the new model now undercuts what K3 charged at launch in July. Highspeed costs exactly double for the same model served faster, which is the same trade Moonshot offers on its K2.7 Code line. ## What Moonshot claims on benchmarks All of these are Moonshot's own figures from its launch post, run with its own harness, and none has independent replication yet. The rows below are the ones most relevant to coding and agent work. Read it with the usual caveats. Moonshot ran K3.1 Pro with the Claude Code harness and took the other models' scores from their own reports or public leaderboards, so the rows mix sources. The Intelligence Index is the one independent line, and there K3.1 Pro sits three points under Opus 5.5 and ten over GLM 5.3. Moonshot says that is an 11-point gain over Kimi K3 on the same index, and the jump within its own line is the clearest signal in the table. Two other claims are worth noting. Moonshot says K3.1 Pro's claim-level hallucination rate on its internal test fell to 8.3% from 23.4% for K3. And it says it identified and removed cyber-related data from mid-training and the RL mix before the open release, trading some vulnerability-research capability for a safer open model. Both are Moonshot's numbers. ## What it means for hardware K3.1 Pro is a post-trained K3, and Moonshot states the parameter counts are unchanged: 2.8 trillion total, 104B active. If the checkpoint ships in the same MXFP4 format as K3, the weights will be about 1.56 TB on disk and the serving requirement is the same multi-node cluster with 2 TB or more of aggregate GPU memory and fast interconnect. Everything in the [Kimi K3 hardware requirements](https://www.yottalabs.ai/post/kimi-k3-hardware-requirements-gpu-memory-2026) post applies until Moonshot publishes a model card that says otherwise. Which means the practical answer is the same one it was for K3. This is a model you call through an API unless you operate a cluster, and 104B active parameters is why the per-token price is what it is. The release of a Flash-class K3.1 would change that, and Moonshot hasn't announced one. ## What a real workload costs Take 10 million input tokens and 2 million output tokens a day, no caching, 30 days. K3.1 Pro lands at half of Muse Wonder's bill and a fifth of GPT-6 Astra's, for a model Moonshot puts within a point of Opus 5.5 on the main coding-agent benchmark. It is still two and a half times the cost of DeepSeek V4 Pro and nearly double GLM 5.3, which is the usual shape of this market: the frontier-adjacent open model costs more per token than the open flagships a tier below it, and the question is whether the capability difference shows up in your output. ## How to use it today Call it on Moonshot's API with the model ID kimi-k3.1-pro, or kimi-k3.1-pro-highspeed if latency matters more than cost. The API is OpenAI-compatible, so an existing client switches with a base URL and a model string. For the models it competes with, [Yotta AI Gateway](https://www.yottalabs.ai/ai-gateway) puts Kimi K3, DeepSeek V4 Pro, GLM 5.3, and Qwen3.8-Max behind one OpenAI-compatible key with flat per-token pricing, so testing K3.1 Pro against them is a model-string change in the same client. The [best Chinese LLMs](https://www.yottalabs.ai/post/best-chinese-llm-models-2026-deepseek-qwen-glm-kimi-compared) roundup covers how those four labs' models split up by job. When the weights land on November 4, the self-hosting route opens for teams with the cluster to run it. We will update this post with the model card details and license when they are published. ## Frequently asked questions **What is Kimi K3.1 Pro?** Moonshot's new flagship, released October 23, 2026. It is a post-trained version of Kimi K3 with the same 2.8T total / 104B active architecture, a 1M-token context, and text and image input. **How much does Kimi K3.1 Pro cost?** $2.00 per million input tokens, $0.20 per million cached input, and $10.00 per million output on Moonshot's API. The Highspeed variant is $4.00 / $0.20 / $20.00. **Is Kimi K3.1 Pro cheaper than Kimi K3?** Yes, by a third on every rate. K3 is $3.00 / $0.30 / $15.00. **Is Kimi K3.1 Pro open source?** Moonshot calls it open weight and says the full weights will be released by November 4, 2026. The license hasn't been announced. Kimi K3 shipped under the custom Kimi K3 License, not an OSI-approved license. **What is the difference between K3.1 Pro and K3.1 Pro Highspeed?** Same model, served two to three times faster according to Moonshot, at double the price. **How does Kimi K3.1 Pro compare to Claude Opus 5.5?** On Moonshot's own numbers, within a point on Terminal-Bench 4.0 (65.7 against 66.4), ahead on DeepSWE v1.1 and SWE-Marathon, and three points behind on the Artificial Analysis Intelligence Index. These are vendor-reported and not yet replicated. **How much VRAM does Kimi K3.1 Pro need?** The same as Kimi K3 if the checkpoint format is unchanged: about 1.56 TB of weights and a multi-node cluster with 2 TB or more of GPU memory. See the Kimi K3 hardware requirements post. **Is Kimi K3.1 Pro on Yotta?** Kimi K3 is live on Yotta AI Gateway at $3.00 per million input and $15.00 per million output, alongside DeepSeek V4 Pro, GLM 5.3, and Qwen3.8-Max. **When will Kimi K3.1 Pro weights be released?** Moonshot says by November 4, 2026. ## Bottom line Kimi K3.1 Pro is the same 2.8T model as K3 with far more post-training, priced a third lower, and Moonshot is claiming frontier-level results on coding-agent benchmarks that no one has independently checked yet. The weights follow in under two weeks, and the hardware story will be K3's hardware story. For most teams the decision is the familiar one. Call it through an API and measure it against the open flagships you already run. On [Yotta AI Gateway](https://www.yottalabs.ai/ai-gateway) that comparison set is one key away, and the [GPT-6 Astra pricing](https://www.yottalabs.ai/post/gpt-6-astra-pricing-api-cost-2026) and [Muse Wonder pricing](https://www.yottalabs.ai/post/meta-muse-wonder-pricing-api-cost-muse-code-plans) posts cover the closed-model side of the same bill.